<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-03510963</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-22T17:22:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Multitask group Lasso for Genome Wide association Studies in diverse populations</title>
            <author role="aut">
              <persName>
                <forename type="first">Chloé-Agathe</forename>
                <surname>Azencott</surname>
              </persName>
              <email type="md5">f1b799b0b2fbba77338e94b166d89ea7</email>
              <email type="domain">mines-paristech.fr</email>
              <idno type="idhal" notation="string">chloe-agathe-azencott</idno>
              <idno type="idhal" notation="numeric">11475</idno>
              <idno type="halauthorid" notation="string">28216-11475</idno>
              <idno type="ARXIV">https://arxiv.org/a/azencott_c_1.html</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1003-301X</idno>
              <idno type="IDREF">https://www.idref.fr/195762959</idno>
              <affiliation ref="#struct-21326"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Asma</forename>
                <surname>Nouira</surname>
              </persName>
              <idno type="halauthorid">1442362-0</idno>
              <affiliation ref="#struct-21326"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Chloé-Agathe</forename>
                <surname>Azencott</surname>
              </persName>
              <email type="md5">fe5b711a5eedb763c16df864c4b2c7af</email>
              <email type="domain">minesparis.psl.eu</email>
            </editor>
            <funder ref="#projanr-48818"/>
            <funder ref="#projanr-50388"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-01-04 16:51:31</date>
              <date type="whenModified">2025-07-03 16:28:02</date>
              <date type="whenReleased">2022-01-04 16:51:31</date>
              <date type="whenProduced">2022-01-03</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="480263">
                <persName>
                  <forename>Chloé-Agathe</forename>
                  <surname>Azencott</surname>
                </persName>
                <email type="md5">fe5b711a5eedb763c16df864c4b2c7af</email>
                <email type="domain">minesparis.psl.eu</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03510963</idno>
            <idno type="halUri">https://minesparis-psl.hal.science/hal-03510963</idno>
            <idno type="halBibtex">azencott:hal-03510963</idno>
            <idno type="halRefHtml">&lt;i&gt;Pacific Symposium on Biocomputing&lt;/i&gt;, Jan 2022, Kohala Coast, Hawaii, United States. pp.163-174</idno>
            <idno type="halRef">Pacific Symposium on Biocomputing, Jan 2022, Kohala Coast, Hawaii, United States. pp.163-174</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENSMP" corresp="PARISTECH">MINES ParisTech</idno>
            <idno type="stamp" n="ENSMP_CBIO" corresp="ENSMP">Bio-informatique (CBIO)</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <idno type="stamp" n="ENSMP_DEP_MS">Département Mathématiques et systèmes</idno>
            <idno type="stamp" n="ENSMP_DR" corresp="ENSMP">ENSMP_DR</idno>
            <idno type="stamp" n="PNRIA">Programme National de Recherche en IA</idno>
            <idno type="stamp" n="ENSMP-PSL" corresp="PSL">MINES ParisTech - École nationale supérieure des mines de Paris - PSL</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="PRAIRIE-IA">PaRis AI Research InstitutE</idno>
            <idno type="stamp" n="ANR-IA-19" corresp="ANR-IA">ANR-IA-19</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Multitask group Lasso for Genome Wide association Studies in diverse populations</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Chloé-Agathe</forename>
                    <surname>Azencott</surname>
                  </persName>
                  <email type="md5">f1b799b0b2fbba77338e94b166d89ea7</email>
                  <email type="domain">mines-paristech.fr</email>
                  <idno type="idhal" notation="string">chloe-agathe-azencott</idno>
                  <idno type="idhal" notation="numeric">11475</idno>
                  <idno type="halauthorid" notation="string">28216-11475</idno>
                  <idno type="ARXIV">https://arxiv.org/a/azencott_c_1.html</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1003-301X</idno>
                  <idno type="IDREF">https://www.idref.fr/195762959</idno>
                  <affiliation ref="#struct-21326"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Asma</forename>
                    <surname>Nouira</surname>
                  </persName>
                  <idno type="halauthorid">1442362-0</idno>
                  <affiliation ref="#struct-21326"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Pacific Symposium on Biocomputing</title>
                  <date type="start">2022-01-03</date>
                  <settlement>Kohala Coast, Hawaii</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <biblScope unit="volume">27</biblScope>
                  <biblScope unit="pp">163-174</biblScope>
                  <date type="datePub">2022-01-04</date>
                </imprint>
              </monogr>
              <idno type="biorxiv">2021.08.02.454499</idno>
              <idno type="pubmed">34890146</idno>
              <idno type="swhid">swh:1:snp:e4e6bd72ddd629c4a0625ee8afcdd9006e942ea2</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Genome-Wide Association Studies, or GWAS, aim at finding Single Nucleotide Polymorphisms (SNPs) that are associated with a phenotype of interest. GWAS are known to suffer from the large dimensionality of the data with respect to the number of available samples. Other limiting factors include the dependency between SNPs, due to linkage disequilibrium (LD), and the need to account for population structure, that is to say, confounding due to genetic ancestry.We propose an efficient approach for the multivariate analysis of multi-population GWAS data based on a multitask group Lasso formulation. Each task corresponds to a subpopulation of the data, and each group to an LD-block. This formulation alleviates the curse of dimensionality, and makes it possible to identify disease LD-blocks shared across populations/tasks, as well as some that are specific to one population/task. In addition, we use stability selection to increase the robustness of our approach. Finally, gap safe screening rules speed up computations enough that our method can run at a genome-wide scale.To our knowledge, this is the first framework for GWAS on diverse populations combining feature selection at the LD-groups level, a multitask approach to address population structure, stability selection, and safe screening rules. We show that our approach outperforms state-of-the-art methods on both a simulated and a real-world cancer datasets.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-21326" status="VALID">
          <idno type="IdRef">152350985</idno>
          <idno type="RNSR">200818048M</idno>
          <idno type="ROR">https://ror.org/00c00ys31</idno>
          <orgName>Centre de Bioinformatique</orgName>
          <orgName type="acronym">CBIO</orgName>
          <date type="start">2006-01-01</date>
          <desc>
            <address>
              <addrLine>60, Boulevard Saint Michel, 75006 PARIS</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://cbio.mines-paristech.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301492" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301492" status="VALID">
          <idno type="IdRef">026375249</idno>
          <idno type="ROR">https://ror.org/04y8cs423</idno>
          <orgName>Mines Paris - PSL (École nationale supérieure des mines de Paris)</orgName>
          <date type="start">1783-01-01</date>
          <desc>
            <address>
              <addrLine>60, boulevard Saint-Michel 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.minesparis.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-48818" status="VALID">
          <idno type="anr">ANR-18-CE45-0021</idno>
          <idno type="program">APPEL À PROJETS GÉNÉRIQUE 2018</idno>
          <orgName>SCAPHE</orgName>
          <desc>Méthodes pour la découverte de combinaisons de SNPs associées avec un phénotype à partir de données génome entier</desc>
          <date type="start">2018</date>
        </org>
        <org type="anrProject" xml:id="projanr-50388" status="VALID">
          <idno type="anr">ANR-19-P3IA-0001</idno>
          <orgName>PRAIRIE</orgName>
          <desc>PaRis Artificial Intelligence Research InstitutE</desc>
          <date type="start">2019</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>